MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641080489 A) filed by Ms. Puppala Sireesha on June 30, 2026, for System And Method For Browser Based Real Time Multimodal Skeletal Data Acquisition With Adaptive Quality Gating For Clinical Gait Analysis.
Inventors include Ms. Puppala Sireesha; Mr. Tanuku Vvs Sai Tejesh; Mr. Kasi Vamshi Mohan; Mr. Preetham Kota; Mr. Yuva Dhanvanth Annabathula; Mr. Shabaz Ahmad Hasib; Mr. Guntu Venkata Pavan Ram Tej; and Ms. Vundavalli Aashna.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: A browser based system acquires multimodal human skeletal data for clinical gait analysis without specialised motion capture hardware. An inference engine (103) runs pose, face, and hand landmarker models within the browser with graphics processing unit acceleration. An adaptive multicriteria quality gate (201) evaluates each frame for landmark completeness, visibility, spatial containment, core joint integrity, and mean visibility, and discards unreliable frames. A subject identity tracker (200) maintains single subject continuity across multiperson frames. Recorded variable rate frames are resampled to a fixed thirty frames per second grid and normalised by root centering, orientation alignment, scale normalisation, confidence masking, and gap interpolation. The processed sequence is serialised within the browser as a Kinect compatible comma separated values file and as a binary NumPy format file, and transmitted to at least one remote storage backend.
Disclaimer: Curated by HT Syndication.
